The decarbonization goals and energy self-sustainability of each country prompts an increase of renewable energy sources such as hydro energy, solar energy, and wind energy. Consequently, the increase of renewable energy sources requires finding of appropriate energy storage solutions, including novel techniques such as hydrogen storage. Solar panels are an appropriate solution for renewable energy harvesting since they can easily be installed even at private houses.

To find the appropriate location for the solar power plant installation it is required to find the location with the best conditions. Three brothers decided that they would invest in solar power plants at the roof of their houses, however they can invest in only one location.

Luckily, they were able to obtain the historical data of solar radiation for locations of their houses. This data can help them identify which location would be the most appropriate one. 


## Problem statement

The problem is that input data has some missing information. It is required to **determine best ML model that will predict Ghi value for next 3 months with most appropriate features** so the best location for installing solars can be determined. 

**Hints:** Evaluate appropriate treatment of missing data (elimination of these records, replacing missing data with some substitute value (imputation methods), etc.)
Explore dimensionality reduction. Features can be omitted, manipulations with the data can be made (e.g. PCA), etc.

The meteorological data is given in a CSV file for 3 separate locations and contains parameters described at the link https://solcast.com/data-parameter-definitions.

The data comprises hour measurements for the period of 3 years. The data consist from all available meteorological data relevant for solar insolation for chosen locations. It is known that GHI component of solar irradiation is most important for determination of solar potential for solar pannels, therefore it is required to predict Ghi value for the period of next 3 months for 3 chosen locations. Some examples of data are shown in table below.